Georgi Gerganov f445c0e68c llama : fix llm_build_k_shift to use correct n_rot (#4889) 2 lat temu
..
__init__.py 34b0a08207 gguf-py: Refactor and allow reading/modifying existing GGUF files (#3981) 2 lat temu
constants.py 83e633c27e llama : differentiate the KV dims in the attention (#4657) 2 lat temu
gguf.py 34b0a08207 gguf-py: Refactor and allow reading/modifying existing GGUF files (#3981) 2 lat temu
gguf_reader.py 34b0a08207 gguf-py: Refactor and allow reading/modifying existing GGUF files (#3981) 2 lat temu
gguf_writer.py 83e633c27e llama : differentiate the KV dims in the attention (#4657) 2 lat temu
py.typed dc07dc492e convert : various script cleanups/fixes + merges and special token handling (#2842) 2 lat temu
tensor_mapping.py f445c0e68c llama : fix llm_build_k_shift to use correct n_rot (#4889) 2 lat temu
vocab.py 880e352277 py : open merges file as 'utf-8' (#4566) 2 lat temu